© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 119154
    Prev
    Next
    INDEX
    Explanations

    conditions and criteria related to computational processes and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odia
    -0.08
    ardon
    -0.07
    FromArray
    -0.07
    ç²
    -0.07
    armor
    -0.06
    æĹ¢çĦ¶
    -0.06
    森
    -0.06
    寸
    -0.06
    iola
    -0.06
    egas
    -0.06
    POSITIVE LOGITS
     thì
    0.11
     then
    0.10
     maka
    0.09
     entonces
    0.09
    ï¼ĮåĪĻ
    0.09
     alors
    0.09
     então
    0.08
    then
    0.08
     ÑĤогда
    0.08
    çļĦè¯Ŀ
    0.08
    Activations Density 0.042%

    No Known Activations